© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 6356
    Prev
    Next
    INDEX
    Explanations

    phrases related to events coming to an end

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating an ending or conclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adding
    -0.70
    reau
    -0.68
     Activities
    -0.65
    xs
    -0.64
     Contributions
    -0.62
     talents
    -0.61
    achu
    -0.60
    ittens
    -0.59
     Experts
    -0.59
     pics
    -0.59
    POSITIVE LOGITS
     snag
    0.85
     conclusion
    0.83
     climax
    0.83
    usterity
    0.80
     lull
    0.79
     whopping
    0.78
     hiatus
    0.77
    士
    0.76
     halt
    0.75
     reckoning
    0.73
    Activations Density 0.133%

    No Known Activations